A Permutation Importance-Based Feature Selection Method for Short-Term Electricity Load Forecasting Using Random Forest

Nantian Huang,Guobo Lu,Dianguo Xu

doi:10.3390/en9100767

Nantian Huang, Guobo Lu + Show 1 more

Open Access

https://doi.org/10.3390/en9100767

Copy DOI

Abstract

The prediction accuracy of short-term load forecast (STLF) depends on prediction model choice and feature selection result. In this paper, a novel random forest (RF)-based feature selection method for STLF is proposed. First, 243 related features were extracted from historical load data and the time information of prediction points to form the original feature set. Subsequently, the original feature set was used to train an RF as the original model. After the training process, the prediction error of the original model on the test set was recorded and the permutation importance (PI) value of each feature was obtained. Then, an improved sequential backward search method was used to select the optimal forecasting feature subset based on the PI value of each feature. Finally, the optimal forecasting feature subset was used to train a new RF model as the final prediction model. Experiments showed that the prediction accuracy of RF trained by the optimal forecasting feature subset was higher than that of the original model and comparative models based on support vector regression and artificial neural network.

Highlights

Load forecast (LF) is the basis for the planning, operating, and scheduling of traditional power networks
By spending a small amount of time, a real preselection feature pre that is much smaller than criteria, namely, mean absolute percentage error (MAPE) and root mean square error (RMSE), are used the original feature can be obtained
A novel feature selection method for short-term load forecast (STLF) is proposed in this paper

Summary

Introduction

Load forecast (LF) is the basis for the planning, operating, and scheduling of traditional power networks. LF is the basis for creating an efficient power system by reducing operational costs and using the renewable energy source of the smart grid [1]. STLF generally refers to the prediction of load one hour, one day, or one week ahead [3]. The prediction accuracy of STLF is directly related to the safety, stability, and economy of power system operation. Considering an electrical utility in the United Kingdom as an example, a decrease of 1% in prediction error can result in a decrease of approximately 10 million pounds in operational costs [4]. In the smart grid and deregulated power market environment, power systems require high prediction accuracy of STLF

Methods

Results

Conclusion